What is LangChain Managed Deep Agents?

Managed Deep Agents (MDA) is the simplest way to build and deploy production agents. You focus on what your agent does, and MDA runs it. You write the agent’s intelligence: its instructions, the tools it can call, the skills it follows, and you select the model that drives it. MDA provides everything underneath: • The Deep Agents harness: The agent loop that plans, calls tools, manages a filesystem, and delegates to subagents. (Deep Agents explained in 1 minute: https://youtu.be/8gCam2-iGLc) • A managed runtime: Every deployment runs on LangSmith Agent Server. You get the Agent Server API, threads, runs, streaming, and the MCP endpoint without operating the server yourself. Learn more about MDA: LangChain Academy (Module 6) → https://academy.langchain.com/courses/foundation-introduction-to-deepagents MDA Virtual Workshop (Recording) → https://events.langchain.com/managed-deep-agents/ Docs → https://docs.langchain.com/langsmith/python/managed-deep-agents-overview